arXiv research

Revisits Lee's Moment Formula, relaxing moment assumptions for implied volatility.

This thesis studies domain adaptation under minimal distribution similarity assumptions using moments.

Independent component analysis (ICA) is the problem of efficiently recovering a matrix $A \in \mathbb{R}^{n\times n}$ from i.i.d. observations of $X=AS$ where $S \in \mathbb{R}^n$ is a random vector with mutually independent coordinates. This problem has been intensively studied, but all existing efficient algorithms w…

The paper analyzes the performance of empirical risk minimization for $p$-norm linear regression.

We discuss the probabilistic properties of the variation based third and fourth moments of financial returns as estimators of the actual moments of the return distributions. The moment variations are defined under non-parametric assumptions with quadratic variation method but for the computational tractability, we use …

New stability framework relaxes boundedness assumptions for generalization bounds.

The study revisits portfolio diversification by relaxing assumptions for skewed, multi-regime, and leptokurtic asset returns.

We show how to compute lower bounds for the supremum Bayes error if the class-conditional distributions must satisfy moment constraints, where the supremum is with respect to the unknown class-conditional distributions. Our approach makes use of Curto and Fialkow's solutions for the truncated moment problem. The lower …

We discuss various aspects of moment map geometry in symplectic and hyperKähler geometry. In particular, we classify complete hyperKähler manifolds of dimension $4n$ with a tri-Hamiltonian action of a torus of dimension $n$, without any assumption on the finiteness of the Betti numbers. As a result we find that the hyp…

We introduce a notion of moment map adapted to actions of Lie groups that preserve a closed three-form. We show existence of our multi-moment maps in many circumstances, including mild topological assumptions on the underlying manifold. Such maps are also shown to exist for all groups whose second and third Lie algebra…

Paper provides Edgeworth expansions for network moments, improving accuracy of sampling distributions.

Paper proposes efficient online estimation of causal effects by deciding which data sources to query.

We provide an approach for learning deep neural net representations of models described via conditional moment restrictions. Conditional moment restrictions are widely used, as they are the language by which social scientists describe the assumptions they make to enable causal inference. We formulate the problem of est…

Classification of SL(n) covariant valuations on Orlicz spaces.

Develops a robust GMM estimator for outlier-tolerant inference.

Uniform deviation bounds limit the difference between a model's expected loss and its loss on an empirical sample uniformly for all models in a learning problem. As such, they are a critical component to empirical risk minimization. In this paper, we provide a novel framework to obtain uniform deviation bounds for loss…

Proposes DWMD for better matching of hidden representations across domains.

This work provides a computationally efficient and statistically consistent moment-based estimator for mixtures of spherical Gaussians. Under the condition that component means are in general position, a simple spectral decomposition technique yields consistent parameter estimates from low-order observable moments, wit…

Several new estimation methods have been recently proposed for the linear regression model with observation error in the design. Different assumptions on the data generating process have motivated different estimators and analysis. In particular, the literature considered (1) observation errors in the design uniformly …

New approach for testable learning using moment matching and Rademacher complexity.

New estimator tackles multi-task linear regression with outliers, avoiding eigenvalue lower bounds.

We derive a general multivariate theory for realised characteristics of `model-free discretisation-invariant swaps', so-called because the standard no-arbitrage assumption of martingale forward prices is sufficient to derive fair-value swap rates for such characteristics which have no jump or discretisation errors. Thi…

Study finds critical points of volume functionals on Sasaki manifolds.

Tensor decomposition methods are popular tools for learning latent variables given only lower-order moments of the data. However, the standard assumption is that we have sufficient data to estimate these moments to high accuracy. In this work, we consider the case in which certain dimensions of the data are not always …

Betas are possibly the most frequently applied tool to analyze how securities relate to the market. While in very widespread use, betas only express dynamics derived from second moment statistics. Financial returns data often deviate from normal assumptions in the sense that they have significant third and fourth order…

Classifies SL(n) covariant matrix-valued valuations on Lp-spaces.

Enhances DP linear regression using public data moments.

Improved Sobolev mappings in Carnot groups with weaker assumptions.

New method finds closest martingale to Brownian motion.

Polynomial-time algorithm learns ReLU networks without assumptions.

We introduce a novel approach, requiring only mild assumptions, for the characterization of deep neural networks at initialization. Our approach applies both to fully-connected and convolutional networks and easily incorporates batch normalization and skip-connections. Our key insight is to consider the evolution with …

Efficiently estimates mean of symmetric distributions without moments.

New algorithm for batch list-decodable linear regression with stronger guarantees.

Derives moments of PL networks for robust DNNs.

Study differentially private linear regression with heavy-tailed data.

Polynomial-time algorithm learns high-dimensional halfspaces without labels.

We show that the conformal structure for the Riemannian analogues of Kerr black-hole metrics can be given an ambitoric structure. We then discuss the properties of the moment maps. In particular, we observe that the moment map image is not locally convex near the singularity corresponding to the ring singularity in the…

Two-dimensional transition rates improve life insurance reserve calculations.

New bounds for neural networks without loss boundedness assumption.

ADOPT optimizes Adam to converge with any β2 without bounded noise.

Dynamic Boltzmann Machine (DyBM) has been shown highly efficient to predict time-series data. Gaussian DyBM is a DyBM that assumes the predicted data is generated by a Gaussian distribution whose first-order moment (mean) dynamically changes over time but its second-order moment (variance) is fixed. However, in many fi…

Study finds the minimum number of finite Gaussian mixtures for best approximation.

Consider a Hamiltonian action of a compact connected Lie group on a conformal symplectic manifold. We prove a convexity theorem for the moment map under the assumption that the action is of Lee type, which establishes an analog of Kirwan's convexity theorem in conformal symplectic geometry.

Let G be a countable group which acts by isometries on a separable, but not necessarily proper, Gromov hyperbolic space X. We say the action of G is weakly hyperbolic if G contains two independent hyperbolic isometries. We show that a random walk on such G converges to the Gromov boundary almost surely. We apply the co…

In this paper, we study the confounder detection problem in the linear model, where the target variable $Y$ is predicted using its $n$ potential causes $X_n=(x_1,...,x_n)^T$. Based on an assumption of rotation invariant generating process of the model, recent study shows that the spectral measure induced by the regress…

Study of hyperkähler reduction on abelian varieties and toric manifolds.

We consider the problem of predicting as well as the best linear combination of d given functions in least squares regression, and variants of this problem including constraints on the parameters of the linear combination. When the input distribution is known, there already exists an algorithm having an expected excess…

Uniformly K-stable toric varieties are asymptotically Chow stable if their Futaki-Ono invariant vanishes.